Graph-based Spatial Transformer with Memory Replay for Multi-future Pedestrian Trajectory Prediction
This work improves trajectory prediction for applications like autonomous driving by enhancing multi-future path generation, though it is incremental as it builds on existing methods.
The paper tackles pedestrian trajectory prediction by generating multiple plausible future paths, addressing issues of smoothness and temporal consistency, and achieves state-of-the-art performance on multi-future prediction with competitive results for single-future prediction.
Pedestrian trajectory prediction is an essential and challenging task for a variety of real-life applications such as autonomous driving and robotic motion planning. Besides generating a single future path, predicting multiple plausible future paths is becoming popular in some recent work on trajectory prediction. However, existing methods typically emphasize spatial interactions between pedestrians and surrounding areas but ignore the smoothness and temporal consistency of predictions. Our model aims to forecast multiple paths based on a historical trajectory by modeling multi-scale graph-based spatial transformers combined with a trajectory smoothing algorithm named ``Memory Replay'' utilizing a memory graph. Our method can comprehensively exploit the spatial information as well as correct the temporally inconsistent trajectories (e.g., sharp turns). We also propose a new evaluation metric named ``Percentage of Trajectory Usage'' to evaluate the comprehensiveness of diverse multi-future predictions. Our extensive experiments show that the proposed model achieves state-of-the-art performance on multi-future prediction and competitive results for single-future prediction. Code released at https://github.com/Jacobieee/ST-MR.